Bao R, Wang B, Wang X, Li H, Zheng R, Rutkowski L, et al. Time-Frequency Token Advantage Clipping for Training Efficient Large Reasoning Model. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 10];40(36):30049-57. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40253